© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111502
    Prev
    Next
    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylon
    -0.27
    classed
    -0.26
    å±ıå¹ķä¸Ĭ
    -0.25
    ÑĮе
    -0.24
    ç»Ļä»ĸ们
    -0.24
    íį¼
    -0.24
    APT
    -0.23
    ìĤ¬ë¥¼
    -0.23
    tees
    -0.23
    ä¸Ģé»ŀ
    -0.23
    POSITIVE LOGITS
     subs
    0.30
    edith
    0.27
    主导
    0.27
     multis
    0.26
    -
    0.26
    :
    0.25
     of
    0.24
    l
    0.24
    0.24
     Determin
    0.24
    Activations Density 0.087%

    No Known Activations